INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.09

3:0.08

4:0.07

5:0.09

6:0.09

7:0.07

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

龍契士

-3.25

jp

-2.95

jpg

-2.79

VG

-2.78

 goblin

-2.66

PS

-2.54

 Flask

-2.50

egal

-2.45

oké

-2.45

 Slack

-2.42

POSITIVE LOGITS

Jah

2.67

 SPORTS

2.61

haw

2.54

abies

2.48

livion

2.48

 reeling

2.47

 Queensland

2.45

 Beir

2.43

yne

2.42

arten

2.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.